@@ -3674,47 +3674,53 @@ v_or_b16_e64_dpp v5, v1, v2 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
36743674v_or_b16_e64_dpp v255, v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
36753675// GFX11: v_or_b16_e64_dpp v255, v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x63,0xd7,0xfa,0xfe,0x03,0x00,0xff,0x6f,0x05,0x30]
36763676
3677- v_pack_b32_f16_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ]
3678- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
3677+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l quad_perm:[3 ,2 ,1 ,0 ]
3678+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
36793679
3680- v_pack_b32_f16_e64_dpp v5, v1, v2 quad_perm:[0 ,1 ,2 ,3 ]
3681- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 quad_perm:[0 ,1 ,2 ,3 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
3680+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l quad_perm:[0 ,1 ,2 ,3 ]
3681+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l quad_perm:[0 ,1 ,2 ,3 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
36823682
3683- v_pack_b32_f16_e64_dpp v5, v1, v2 row_mirror
3684- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
3683+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_mirror
3684+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
36853685
3686- v_pack_b32_f16_e64_dpp v5, v1, v2 row_half_mirror
3687- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
3686+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_half_mirror
3687+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
36883688
3689- v_pack_b32_f16_e64_dpp v5, v1, v2 row_shl:1
3690- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
3689+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shl:1
3690+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
36913691
3692- v_pack_b32_f16_e64_dpp v5, v1, v2 row_shl:15
3693- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
3692+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shl:15
3693+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
36943694
3695- v_pack_b32_f16_e64_dpp v5, v1, v2 row_shr:1
3696- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
3695+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shr:1
3696+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
36973697
3698- v_pack_b32_f16_e64_dpp v5, v1, v2 row_shr:15
3699- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
3698+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shr:15
3699+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
37003700
3701- v_pack_b32_f16_e64_dpp v5, v1, v2 row_ror:1
3702- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
3701+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_ror:1
3702+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
37033703
3704- v_pack_b32_f16_e64_dpp v5, v1, v2 row_ror:15
3705- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
3704+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_ror:15
3705+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
37063706
3707- v_pack_b32_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf
3708- // GFX11: v_pack_b32_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
3707+ v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_share:0 row_mask:0xf bank_mask:0xf
3708+ // GFX11: v_pack_b32_f16_e64_dpp v5, v1.l , v2.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x11,0xd7,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
37093709
3710- v_pack_b32_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1
3711- // GFX11: v_pack_b32_f16_e64_dpp v5, |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x11,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01]
3710+ v_pack_b32_f16_e64_dpp v5, |v1.l |, -v2.l row_share:15 row_mask:0x0 bank_mask:0x1
3711+ // GFX11: v_pack_b32_f16_e64_dpp v5, |v1.l |, -v2.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x11,0xd7,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01]
37123712
3713- v_pack_b32_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi: 0
3714- // GFX11: v_pack_b32_f16_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x02,0x11,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
3713+ v_pack_b32_f16_e64_dpp v5, -v1.l , |v2.l | row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
3714+ // GFX11: v_pack_b32_f16_e64_dpp v5, -v1.l , |v2.l | row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x02,0x11,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
37153715
3716- v_pack_b32_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
3717- // GFX11: v_pack_b32_f16_e64_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x03,0x11,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
3716+ v_pack_b32_f16_e64_dpp v255, -|v255.l|, -|v255.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
3717+ // GFX11: v_pack_b32_f16_e64_dpp v255, -|v255.l|, -|v255.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x03,0x11,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
3718+
3719+ v_pack_b32_f16_e64_dpp v5, -v1.h, |v2.l| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
3720+ // GFX11: v_pack_b32_f16_e64_dpp v5, -v1.h, |v2.l| op_sel:[1 ,0 ,0 ] row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x0a,0x11,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
3721+
3722+ v_pack_b32_f16_e64_dpp v255, -|v255.l|, -|v255.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
3723+ // GFX11: v_pack_b32_f16_e64_dpp v255, -|v255.l|, -|v255.h| op_sel:[0 ,1 ,0 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x13,0x11,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
37183724
37193725v_perm_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3 ,2 ,1 ,0 ]
37203726// GFX11: v_perm_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x44,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
@@ -4611,11 +4617,11 @@ v_min3_u16_e64_dpp v5, v1, v2, -1 op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank
46114617v_min3_u16_e64_dpp v255, v255, v255, src_scc op_sel:[0 ,0 ,0 ,1 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1
46124618// GFX11: v_min3_u16_e64_dpp v255, v255, v255, src_scc op_sel:[0 ,0 ,0 ,1 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x40,0x4b,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x0d,0x30]
46134619
4614- v_pack_b32_f16_e64_dpp v5, -v1, |v2| op_sel:[1 ,0 ,0 ] row_xmask:0 row_mask:0x1 bank_mask:0x3
4615- // GFX11: v_pack_b32_f16_e64_dpp v5, -v1, |v2| op_sel:[1 ,0 ,0 ] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x0a,0x11,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13]
4620+ v_pack_b32_f16_e64_dpp v5, -v1.h , |v2.l | op_sel:[1 ,0 ,0 ] row_xmask:0 row_mask:0x1 bank_mask:0x3
4621+ // GFX11: v_pack_b32_f16_e64_dpp v5, -v1.h , |v2.l | op_sel:[1 ,0 ,0 ] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x0a,0x11,0xd7,0xfa,0x04,0x02,0x20,0x01,0x60,0x01,0x13]
46164622
4617- v_pack_b32_f16_e64_dpp v255, -|v255|, -|v255| op_sel:[0 ,1 ,0 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1
4618- // GFX11: v_pack_b32_f16_e64_dpp v255, -|v255|, -|v255| op_sel:[0 ,1 ,0 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x13,0x11,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30]
4623+ v_pack_b32_f16_e64_dpp v255, -|v255.l |, -|v255.h | op_sel:[0 ,1 ,0 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1
4624+ // GFX11: v_pack_b32_f16_e64_dpp v255, -|v255.l |, -|v255.h | op_sel:[0 ,1 ,0 ] row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x13,0x11,0xd7,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x0d,0x30]
46194625
46204626v_dot2_f16_f16_e64_dpp v0.l, v1, v2, v3.l quad_perm:[0 ,1 ,2 ,3 ] row_mask:0x0 bank_mask:0x0 fi:1
46214627// GFX11: v_dot2_f16_f16_e64_dpp v0.l, v1, v2, v3.l quad_perm:[0 ,1 ,2 ,3 ] row_mask:0x0 bank_mask:0x0 fi:1 ; encoding: [0x00,0x00,0x66,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x04,0x00]
0 commit comments